Incorporating bevacizumab in a chemotherapy regimen (7.5 mg/kg every 3 weeks for five or six cycles) and then continuing bevacizumab alone for a total of 12 months of treatment extended ...progression-free survival in advanced and high-risk early-stage ovarian cancer.
Epithelial ovarian cancer and related cancers lead to 15,000 deaths in the United States annually, representing the fifth leading cause of death from cancer among women.
1
The poor prognosis is usually attributed to advanced stage at diagnosis and inadequate chemotherapy.
Vascular endothelial growth factor (VEGF) and angiogenesis are important promoters of ovarian-cancer progression.
2
–
6
Both correlate directly with the extent of disease and inversely with progression-free survival
7
–
9
and overall survival,
8
,
10
–
13
often independently of known prognostic factors.
7
–
10
,
12
,
13
Bevacizumab, a humanized VEGF-neutralizing monoclonal antibody, inhibits tumor angiogenesis
14
and has shown single-agent activity in phase 2 epithelial . . .
•We especially focused on the latest unsupervised/self-supervised and semi-supervised learning methods in medical image analysis.•We comprehensively summarized the research progress of deep learning ...technology in four different medical image analysis tasks.•Representative architectures were introduced for each task, such as Transformer-based frameworks for segmentation.•We discussed several aspects that are important to achieving large-scale applications of deep learning in clinical settings.•More than 200 recently published papers were reviewed in this review paper.
Deep learning has received extensive research interest in developing new medical image processing algorithms, and deep learning based models have been remarkably successful in a variety of medical imaging tasks to support disease detection and diagnosis. Despite the success, the further improvement of deep learning models in medical image analysis is majorly bottlenecked by the lack of large-sized and well-annotated datasets. In the past five years, many studies have focused on addressing this challenge. In this paper, we reviewed and summarized these recent studies to provide a comprehensive overview of applying deep learning methods in various medical image analysis tasks. Especially, we emphasize the latest progress and contributions of state-of-the-art unsupervised and semi-supervised deep learning in medical image analysis, which are summarized based on different application scenarios, including classification, segmentation, detection, and image registration. We also discuss major technical challenges and suggest possible solutions in the future research efforts.
Summary Background Platinum-based chemotherapy doublets are a standard of care for women with ovarian cancer recurring 6 months after completion of initial therapy. In this study, we aimed to explore ...the roles of secondary surgical cytoreduction and bevacizumab in this population, and report the results of the bevacizumab component here. Methods The multicentre, open-label, randomised phase 3 GOG-0213 trial was done in 67 predominantly academic centres in the USA (65 centres), Japan (one centre), and South Korea (one centre). Eligible patients were adult women (aged ≥18 years) with recurrent measurable or evaluable epithelial ovarian, primary peritoneal, or fallopian tube cancer, and a clinical complete response to primary platinum-based chemotherapy, who had been disease-free for at least 6 months following last infused cycle of platinum. Patients were randomly assigned (1:1) to standard chemotherapy (six 3-weekly cycles of paclitaxel 175 mg/m2 of body surface area and carboplatin area under the curve 5) or the same chemotherapy regimen plus bevacizumab (15 mg/kg of bodyweight) every 3 weeks and continued as maintenance every 3 weeks until disease progression or unacceptable toxicity. Individuals who participated in both the bevacizumab objective and surgical objective (which is ongoing) were randomly assigned (1:1:1:1) to receive either of these two chemotherapy regimens with or without prior secondary cytoreductive surgery. Randomisation for the bevacizumab objective was stratified by treatment-free interval and participation in the surgical objective. The primary endpoint was overall survival, analysed by intention to treat. This study is registered with ClinicalTrials.gov , number NCT00565851. Findings Between Dec 10, 2007, and Aug 26, 2011, 674 women were enrolled and randomly assigned to standard chemotherapy (n=337) or chemotherapy plus bevacizumab (n=377). Median follow-up at the end of the trial on Nov 5, 2014, was 49·6 months in each treatment group (IQR 41·5–62·2 for chemotherapy plus bevacizumab; IQR 40·8–59·3 for chemotherapy), at which point 415 patients had died (214 in the chemotherapy group and 201 in the chemotherapy plus bevacizumab group). Based on pretreatment stratification data, median overall survival in the chemotherapy plus bevacizumab group was 42·2 months (95% CI 37·7–46·2) versus 37·3 months (32·6–39·7) in the chemotherapy group (hazard ratio HR 0·829; 95% CI 0·683–1·005; p=0·056). We identified incorrect treatment-free interval stratification data for 45 (7%) patients (equally balanced between treatment groups); a sensitivity analysis of overall survival based on the audited treatment-free interval stratification data gave an adjusted HR of 0·823 (95% CI 0·680–0·996; p=0·0447). In the safety population (all patients who initiated treatment), 317 (96%) of 325 patients in the chemotherapy plus bevacizumab group had at least one grade 3 or worse adverse event compared with 282 (86%) of 332 in the chemotherapy group; the most frequently reported of these in the chemotherapy plus bevacizumab group compared with the chemotherapy group were hypertension (39 12% vs two 1%), fatigue (27 8% vs eight 2%), and proteinuria (27 8% vs none). Two (1%) treatment-related deaths occurred in the chemotherapy group (infection n=1 and myelodysplastic syndrome n=1) compared with nine (3%) in the chemotherapy plus bevacizumab group (infection n=1, febrile neutropenia n=1, myelodysplastic syndrome n=1, secondary malignancy n=1; deaths not classified with CTCAE terms: disease progression n=3, sudden death n=1, and not specified n=1). Interpretation The addition of bevacizumab to standard chemotherapy, followed by maintenance therapy until progression, improved the median overall survival in patients with platinum-sensitive recurrent ovarian cancer. Although the intention-to-treat analysis for overall survival was not significant, our sensitivity analysis based on corrected treatment-free interval stratification indicates that this strategy might be an important addition to the therapeutic armamentarium in these patients. Funding National Cancer Institute and Genentech.
We report the final, protocol-specified analysis of overall survival (OS) in GOG-0218, a phase III, randomized trial of bevacizumab in women with newly diagnosed ovarian, fallopian tube, or primary ...peritoneal carcinoma.
A total of 1,873 women with incompletely resected stage III to IV disease were randomly assigned 1:1:1 to six 21-day cycles of intravenous carboplatin (area under the concentration
time curve 6) and paclitaxel (175 mg/m
) versus chemotherapy plus concurrent bevacizumab (15 mg/kg, cycles 2 to 6) versus chemotherapy plus concurrent and maintenance bevacizumab (cycles 2 to 22). Inclusion criteria included a Gynecologic Oncology Group performance status of 0 to 2 and no history of clinically significant vascular events or evidence of intestinal obstruction. OS was analyzed in the intention-to-treat population. A total of 1,195 serum and/or tumor specimens were sequenced for
and damaging mutations in homologous recombination repair (HRR) genes. Intratumoral microvessel density was studied using CD31 immunohistochemistry.
Median follow-up was 102.9 months. Relative to control (n = 625), for patients receiving bevacizumab-concurrent (n = 625), the hazard ratio (HR) of death was 1.06 (95% CI, 0.94 to 1.20); for bevacizumab-concurrent plus maintenance (n = 623), the HR was 0.96 (95% CI, 0.85 to 1.09). Disease-specific survival was not improved in any arm. No survival advantage was observed after censoring patients who received bevacizumab at crossover or as second line. Median OS for stage IV bevacizumab-concurrent plus maintenance was 42.8
32.6 months for stage IV control (HR, 0.75; 95% CI, 0.59 to 0.95). Relative to wild type, the HR for death for
mutated carcinomas was 0.62 (95% CI, 0.52 to 0.73), and for non-
HRR, the HR was 0.65 (95% CI, 0.51 to 0.85).
, HRR, and CD31 were not predictive of bevacizumab activity.
No survival differences were observed for patients who received bevacizumab compared with chemotherapy alone. Testing for
mutations and homologous recombination deficiency is essential.
The primary objective was to determine if vaginal cuff brachytherapy and chemotherapy (VCB/C) increases recurrence-free survival (RFS) compared with pelvic radiation therapy (RT) in high-intermediate ...and high-risk early-stage endometrial carcinoma.
A randomized phase III trial was performed in eligible patients with endometrial cancer. Eligible patients had International Federation of Gynecology and Obstetrics (2009) stage I endometrioid histology with Gynecologic Oncology Group protocol 33-based high-intermediate-risk criteria, stage II disease, or stage I to II serous or clear cell tumors. Treatment was randomly assigned between RT (45 to 50.4 Gy over 5 weeks) or VCB followed by intravenous paclitaxel 175 mg/m
(3 hours) plus carboplatin (area under the curve, 6) every 21 days for three cycles.
The median age of the 601 patients was 63 years, and 74% had stage I disease. Histologies included endometrioid (71%), serous (15%), and clear cell (5%). With a median follow-up of 53 months, the 60-month RFS was 0.76 (95% CI, 0.70 to 0.81) for RT and 0.76 (95% CI, 0.70 to 0.81) for VCB/C (hazard ratio, 0.92; 90% confidence limit, 0.69 to 1.23). The 60-month overall survival was 0.87 (95% CI, 0.83 to 0.91) for RT and 0.85 (95% CI, 0.81 to 0.90) for VCB/C (hazard ratio, 1.04; 90% confidence limit, 0.71 to 1.52). Vaginal and distant recurrence rates were similar between arms. Pelvic or para-aortic nodal recurrences were more common with VCB/C (9%
4%). There was no heterogeneity of treatment effect with respect to RFS or overall survival among clinical or pathologic variables evaluated.
Superiority of VCB/C compared with pelvic RT was not demonstrated. Acute toxicity was greater with VCB/C; late toxicity was similar. Pelvic RT alone remains an effective, well-tolerated, and appropriate adjuvant treatment in high-risk early-stage endometrial carcinomas of all histologies.
Limitations of the paclitaxel-doxorubicin-cisplatin (TAP) regimen in the treatment of endometrial cancer include tolerability and cumbersome scheduling. The Gynecologic Oncology Group studied ...carboplatin plus paclitaxel (TC) as a noninferior alternative to TAP.
GOG0209 was a phase III, randomized, noninferiority, open-label trial. Inclusion criteria were stage III, stage IV, and recurrent endometrial cancers; performance status 0-2; and adequate renal, hepatic, and marrow function. Prior radiotherapy and/or hormonal therapy were permitted, but chemotherapy, including radiosensitization, was not. Patients were treated with doxorubicin 45 mg/m
and cisplatin 50 mg/m
(day 1), followed by paclitaxel 160 mg/m
(day 2) with granulocyte colony-stimulating factor or paclitaxel 175 mg/m
and carboplatin area under the curve 6 (day 1) every 21 days for seven cycles. The primary endpoint was overall survival (OS; modified intention to treat). Progression-free survival (PFS), health-related quality of life (HRQoL), and toxicity were secondary endpoints.
From 2003 to 2009, 1,381 women were enrolled. Noninferiority of TC to TAP was concluded for OS (median, 37
41 months, respectively; hazard ratio HR, 1.002; 90% CI, 0.9 to 1.12), and PFS (median, 13
14 months; HR, 1.032; 90% CI, 0.93 to 1.15). Neutropenic fever was reported in 7% of patients receiving TAP and 6% of those receiving TC. Grade > 2 sensory neuropathy was recorded in 26% of patients receiving TAP and 20% receiving TC (
= .40). More grade ≥ 3 thrombocytopenia (23%
12%), vomiting (7%
4%), diarrhea (6%
2%), and metabolic (14%
8%) toxicities were reported with TAP. Neutropenia (52%
80%) was more common with TC. Small HRQoL differences favored TC.
With demonstrated noninferiority to TAP, TC is the global first-line standard for advanced endometrial cancer.
To evaluate the impact of two different intraperitoneal (IP) chemotherapy regimens on progression-free survival (PFS) among women with newly diagnosed advanced ovarian carcinoma.
Eligible patients ...were randomly assigned to six cycles of IV paclitaxel 80 mg/m
once per week with intravenous (IV) carboplatin area under the curve 6 (IV carboplatin) versus IV paclitaxel 80 mg/m
once per week with IP carboplatin area under the curve 6 (IP carboplatin) versus once every 3 weeks IV paclitaxel 135 mg/m
over 3 hours day 1, IP cisplatin 75 mg/m
day 2, and IP paclitaxel 60 mg/m
day 8 (IP cisplatin). All participants received bevacizumab 15 mg/kg IV every 3 weeks in cycles 2 to 22.
A total of 1,560 participants were enrolled and had 84.8 months of follow-up. The median PFS duration was 24.9 months in the IV carboplatin arm, 27.4 months in the IP carboplatin arm, and 26.2 months in the IP cisplatin arm. For the subgroup of 1,380 patients with stage II/III and residual disease of 1 cm or less, median PFS was 26.9 (IV-carboplatin), 28.7 (IP-carboplatin), and 27.8 months (IP cisplatin), respectively. Median PFS for patients with stage II/III and no residual disease was 35.9, 38.8, and 35.5 months, respectively. Median overall survival for all enrolled was 75.5, 78.9, and 72.9 months, respectively, and median overall survival for stage II/III with no gross residual disease was 98.8 months, 104.8 months, and not reached. Mean patient-reported Functional Assessment of Cancer Therapy neurotoxicity scores (Gynecologic Oncology Group) were similar for all arms, but the mean Trial Outcome Index of the Functional Assessment of Cancer Therapy-Ovary scores during chemotherapy were statistically worse in the IP cisplatin arm.
Compared with the IV carboplatin reference arm, the duration of PFS was not significantly increased with either IP regimen when combined with bevacizumab and was better tolerated than IP cisplatin.
The primary objective was to establish noninferiority of laparoscopy compared with laparotomy for recurrence after surgical staging of uterine cancer.
Patients with clinical stages I to IIA disease ...were randomly allocated (two to one) to laparoscopy (n = 1,696) versus laparotomy (n = 920) for hysterectomy, salpingo-oophorectomy, pelvic cytology, and pelvic and para-aortic lymphadenectomy. The primary study end point was noninferiority of recurrence-free interval defined as no more than a 40% increase in the risk of recurrence with laparoscopy compared with laparotomy.
With a median follow-up time of 59 months for 2,181 patients still alive, there were 309 recurrences (210 laparoscopy; 99 laparotomy) and 350 deaths (229 laparoscopy; 121 laparotomy). The estimated hazard ratio for laparoscopy relative to laparotomy was 1.14 (90% lower bound, 0.92; 95% upper bound, 1.46), falling short of the protocol-specified definition of noninferiority. However, the actual recurrence rates were substantially lower than anticipated, resulting in an estimated 3-year recurrence rate of 11.4% with laparoscopy and 10.2% with laparotomy, or a difference of 1.14% (90% lower bound, -1.28; 95% upper bound, 4.0). The estimated 5-year overall survival was almost identical in both arms at 89.8%.
This study previously reported that laparoscopic surgical management of uterine cancer is superior for short-term safety and length-of-stay end points. The potential for increased risk of cancer recurrence with laparoscopy versus laparotomy was quantified and found to be small, providing accurate information for decision making for women with uterine cancer.
We hypothesized that mutations in homologous recombination repair (HRR) genes beyond
and
improve outcomes for ovarian carcinoma patients treated with platinum therapy and would impact the relative ...benefit of adding prolonged bevacizumab.
We sequenced DNA from blood and/or neoplasm from 1,195 women enrolled in GOG-0218, a randomized phase III trial in advanced ovarian carcinoma of bevacizumab added to carboplatin and paclitaxel. Defects in HRR were defined as damaging mutations in 16 genes. Proportional hazards models were used to estimate relative hazards for progression-free survival (PFS) and overall survival (OS).
Of 1,195 women with ovarian carcinoma, HRR mutations were identified in 307 (25.7%). Adjusted hazards for progression and death compared with those without mutations were lower for women with non-
HRR mutations HR = 0.73; 95% confidence interval (CI), 0.57-0.94;
= 0.01 for PFS; HR = 0.67; 95% CI, 0.50-0.90;
= 0.007 for OS and
mutations (HR = 0.80; 95% CI, 0.66-0.97;
= 0.02 for PFS; HR = 0.74; 95% CI, 0.59-0.94;
= 0.01 for OS) and were lowest for
mutations (HR = 0.52; 95% CI, 0.40-0.67;
< 0.0001 for PFS; HR = 0.36; 95% CI, 0.25-0.53;
< 0.0001 for OS). A test of interaction showed no difference in the effect of bevacizumab on PFS between cases with and without mutations.
HRR mutations, including non-
genes, significantly prolong PFS and OS in ovarian carcinoma and should be stratified for in clinical trials. The benefit of adding bevacizumab was not significantly modified by mutation status.
.
The objective was to compare laparoscopy versus laparotomy for comprehensive surgical staging of uterine cancer.
Patients with clinical stage I to IIA uterine cancer were randomly assigned to ...laparoscopy (n = 1,696) or open laparotomy (n = 920), including hysterectomy, salpingo-oophorectomy, pelvic cytology, and pelvic and para-aortic lymphadenectomy. The main study end points were 6-week morbidity and mortality, hospital length of stay, conversion from laparoscopy to laparotomy, recurrence-free survival, site of recurrence, and patient-reported quality-of-life outcomes.
Laparoscopy was initiated in 1,682 patients and completed without conversion in 1,248 patients (74.2%). Conversion from laparoscopy to laparotomy was secondary to poor visibility in 246 patients (14.6%), metastatic cancer in 69 patients (4.1%), bleeding in 49 patients (2.9%), and other cause in 70 patients (4.2%). Laparoscopy had fewer moderate to severe postoperative adverse events than laparotomy (14% v 21%, respectively; P < .0001) but similar rates of intraoperative complications, despite having a significantly longer operative time (median, 204 v 130 minutes, respectively; P < .001). Hospitalization of more than 2 days was significantly lower in laparoscopy versus laparotomy patients (52% v 94%, respectively; P < .0001). Pelvic and para-aortic nodes were not removed in 8% of laparoscopy patients and 4% of laparotomy patients (P < .0001). No difference in overall detection of advanced stage (stage IIIA, IIIC, or IVB) was seen (17% of laparoscopy patients v 17% of laparotomy patients; P = .841).
Laparoscopic surgical staging for uterine cancer is feasible and safe in terms of short-term outcomes and results in fewer complications and shorter hospital stay. Follow-up of these patients will determine whether surgical technique impacts pattern of recurrence or disease-free survival.