•A DCNN-based fully automatic thrombus detection and segmentation pipeline that is easily translatable to clinical practice is proposed.•A new DCNN architecture adapted to post-operative thrombus ...segmentation from CTA images is presented, which combines low level features with coarser representations.•The well-known Detectnet computer vision network is translated into the clinical domain, specifically for thrombus region of interest detection in CTA images.•Automatic segmentation exceeds previous state of the art results, with a mean Dice similarity coefficient of 82%.•In terms of clinical applicability, the obtained segmentation results lay within the experienced human observer variance without the need of human intervention in most common cases.
Display omitted
Computerized Tomography Angiography (CTA) based follow-up of Abdominal Aortic Aneurysms (AAA) treated with Endovascular Aneurysm Repair (EVAR) is essential to evaluate the progress of the patient and detect complications. In this context, accurate quantification of post-operative thrombus volume is required. However, a proper evaluation is hindered by the lack of automatic, robust and reproducible thrombus segmentation algorithms. We propose a new fully automatic approach based on Deep Convolutional Neural Networks (DCNN) for robust and reproducible thrombus region of interest detection and subsequent fine thrombus segmentation. The DetecNet detection network is adapted to perform region of interest extraction from a complete CTA and a new segmentation network architecture, based on Fully Convolutional Networks and a Holistically-Nested Edge Detection Network, is presented. These networks are trained, validated and tested in 13 post-operative CTA volumes of different patients using a 4-fold cross-validation approach to provide more robustness to the results. Our pipeline achieves a Dice score of more than 82% for post-operative thrombus segmentation and provides a mean relative volume difference between ground truth and automatic segmentation that lays within the experienced human observer variance without the need of human intervention in most common cases.
•Modified holistically-nested edge detection network for breast pectoral muscle segmentation.•Largest evaluation in the literature to date with over 1000 breast pectoral muscle boundaries in MLO ...mammograms.•A fully automated method to automatically model the appearance of pectoral muscle boundaries.•Experimental results suggest that a contour-based CNN approach reduces false positives in comparison to region/path-based CNN results.
Display omitted
This paper presents a method for automatic breast pectoral muscle segmentation in mediolateral oblique mammograms using a Convolutional Neural Network (CNN) inspired by the Holistically-nested Edge Detection (HED) network. Most of the existing methods in the literature are based on hand-crafted models such as straight-line, curve-based techniques or a combination of both. Unfortunately, such models are insufficient when dealing with complex shape variations of the pectoral muscle boundary and when the boundary is unclear due to overlapping breast tissue. To compensate for these issues, we propose a neural network framework that incorporates multi-scale and multi-level learning, capable of learning complex hierarchical features to resolve spatial ambiguity in estimating the pectoral muscle boundary. For this purpose, we modified the HED network architecture to specifically find ‘contour-like’ objects in mammograms. The proposed framework produced a probability map that can be used to estimate the initial pectoral muscle boundary. Subsequently, we process these maps by extracting morphological properties to find the actual pectoral muscle boundary. Finally, we developed two different post-processing steps to find the actual pectoral muscle boundary. Quantitative evaluation results show that the proposed method is comparable with alternative state-of-the-art methods producing on average values of 94.8 ± 8.5% and 97.5 ± 6.3% for the Jaccard and Dice similarity metrics, respectively, across four different databases.
Abstract
OBJECTIVES
This analysis aimed to evaluate perioperative outcomes of surgical resection following neoadjuvant treatment with chemotherapy plus nivolumab in resectable stage IIIA ...non-small-cell lung cancer.
METHODS
Eligible patients received neoadjuvant chemotherapy (paclitaxel + carboplatin) plus nivolumab for 3 cycles. Reassessment of the tumour was carried out after treatment and patients with at least stable disease as best response underwent pulmonary resection. After surgery, patients received adjuvant treatment with nivolumab for 1 year. Surgical data were collected from the NADIM database and patient charts were reviewed for additional surgical details.
RESULTS
Among 46 patients who received neoadjuvant treatment, 41 (89.1%) underwent surgery. Two patients rejected surgery and 3 did not fulfil resectability criteria. There were 35 lobectomies (85.3%), 3 of which were sleeve lobectomies (9.4%), 3 bilobectomies (7.3%) and 3 pneumonectomies (7.3%). Video-assisted thoracoscopy was the initial approach in 51.2% of cases, with a conversion rate of 19% (n = 4). There was no operative mortality at either 30 or 90 days. The most common complications were prolonged air leak (n = 8), pneumonia (n = 5) and arrhythmia (n = 4). Complete resection (R0) was achieved in all patients who underwent surgery, downstaging was observed in 37 patients (90.2%) and major pathological response in 34 patients (82.9%).
CONCLUSIONS
Surgical resection following induction therapy with chemotherapy plus nivolumab appears to be safe and offers appropriate oncological outcomes. Perioperative morbidity and mortality rates in our study were no higher than previously reported in this setting. A minimally invasive approach is, therefore, feasible.
Robotic-assisted thoracic surgery (RATS) is used increasingly frequently in major lung resection for early stage non-small-cell lung cancer (NSCLC) but has not yet been fully evaluated. The aim of ...this study was to compare the surgical outcomes of lymph node dissection (LND) performed via RATS with those from totally thoracoscopic (TT) four-port videothoracoscopy.
Clinical and pathological data were collected retrospectively from patients with clinical stage N0 NSCLC who underwent pulmonary resection in the form of lobectomy or segmental resection between June 2010 and November 2022. The assessment criteria were number of mediastinal lymph nodes and number of mediastinal stations dissected via the RATS approach compared with the four-port TT approach.
A total of 246 pulmonary resections with LND for clinical stages I-II NSCLC were performed: 85 via TT and 161 via RATS. The clinical characteristics of the patients were similar in both groups. The number of mediastinal nodes dissected and mediastinal stations dissected was significantly higher in the RATS group (TT: mean ± SD, 10.72 ± 3.7; RATS, 14.74 ± 6.3
< 0.001), except in the inferior mediastinal stations. There was no difference in terms of postoperative complications.
In patients with early stage NSCLC undergoing major lung resection, the quality of hilomediastinal LND performed using RATS was superior to that performed using TT.
•We present a hypergraph representation of the abdominal arterial system as a family tree using a probabilistic graph matching framework.•In topology, the de fined family tree model is used for ...topological recognition of the abdominal artery system, and it is optimized by an HMM with a Markov chain.•For geometry, we use XGBoost ensemble learning with intrinsic geometric features for branch level labeling.
Automated anatomical vessel labeling of the abdominal arterial system is a crucial topic in medical image processing. One reason for this is the importance of the abdominal arterial system in the human body, and another is that such labeling is necessary for the related disease diagnoses, treatments and epidemiological population analyses. We define a hypergraph representation of the abdominal arterial system as a family tree model with a probabilistic hypergraph matching framework for automated vessel labeling. Then we treat the labelling problem as the convex optimization problem and solve it with the maximum a posteriori(MAP) combined the likelihood obtained by geometric labelling with the family tree topology-based knowledge. Geometrically, we utilize XGBoost ensemble learning with an intrinsic geometric feature importance analysis for branch-level labeling. In topology, the defined family tree model of the abdominal arterial system is transferred as a Markov chain model using a constrained traversal order method and further the Markov chain model is optimized by a hidden Markov model (HMM). The probability distribution of the target branches for each candidate anatomical name is predicted and effectively embedded in the HMM model. This approach is evaluated with the leave-one-out method on 37 clinical patients’ abdominal arteries, and the average accuracy is 91.94%. The obtained results are better than those of the state-of-art method with an F1 score of 93.00% and a recall of 93.00%, as the proposed method simultaneously handles the anatomical structural variability and discriminates between the symmetric branches. It is demonstrated to be suitable for labelling branches of the abdominal arterial system and can also be extended to similar tubular organ networks, such as arterial or airway networks.
The aim of this study was to assess the effect of the lymphocyte-to-monocyte ratio (LMR), neutrophil-to-lymphocyte ratio and platelet-to-lymphocyte ratio on overall survival and disease-free survival ...in patients with lung cancer treated with radical surgery.
We performed a retrospective review of patients with lung cancer who prospectively underwent radical resection between 2004 and 2012. Blood samples were taken as part of the preoperative workup. The inflammatory markers studied were absolute values of lymphocytes, monocytes, neutrophils and platelets, with subsequent calculation of ratios. Median follow-up was 52 months.
Two hundred and sixty-eight patients underwent surgery, of whom 218 (81.3%) were men. Mean age was 62.9 ± 8.7 years. A lymphocyte-to-monocyte ratio ≥ 2.5 was independently associated with longer disease-free survival (hazard ratio HR 0.476 (0.307-0.738), p = 0.001) and longer overall survival (HR, 0.546; 95% CI: 0.352-0.846; p = 0.007), in models adjusted for age, sex, stage, and type of resection. No other systemic inflammatory marker showed a significant association.
Preoperative LMR is an independent prognostic factor of overall survival and recurrence-free survival in patients with surgically-resected early stage lung cancer.
The relapse rate in non-small cell lung cancer (NSCLC) is high, even in localized disease, suggesting that the current approach to pathological staging is insufficiently sensitive to detect occult ...micrometastases present in resected lymph nodes. Therefore, we aimed to determine the prognostic value of the expression of embryonic molecular markers in histologically-negative lymph nodes of completely-resected NSCLC.
76 completely-resected NSCLC patients were included: 60 pN0 and 16 pN1. Primary tumors and 347 lymph node were studied. CEACAM5, FGFR2b, and PTPN11 expression levels were evaluated through mRNA analysis using real-time RT-qPCR assay. Statistical analyses included the Kruskal-Wallis test, Kaplan Meier curves, and log-rank tests.
CEACAM5 expression levels were scored as high in of 90 lymph nodes (26%). The molecular-positive lymph nodes lead to the restaging of 37 (62%) pN0 patients as molecular N1 or N2 and 5 (31%) pN1 cases were reclassified as molecular-positive N2. Surprisingly, molecular-positive patients associated with a better OS (overall survival, p = 0,04). FGFR2b overexpression was observed in 41 (12%) lymph nodes leading to the restaging of 17 patients (22%). Again a trend was observed toward a better DFS (disease-free survival) in the restaged patients (p = 0,09). Accordingly, high expression levels of CEACAM5 or FGFR2b in the primary were related to better DFS (p = 0,06; p < 0,02, respectively).
Molecular nodal restaging based on expression levels of CEACAM5 and/or FGFR2b, does not add relevant clinical information to pathological staging of NSCLC likely related to the better prognosis of their overexpression in primary tumors.
The status of the data-driven management of cancer care as well as the challenges, opportunities, and recommendations aimed at accelerating the rate of progress in this field are topics of great ...interest. Two international workshops, one conducted in June 2019 in Cordoba, Spain, and one in October 2019 in Athens, Greece, were organized by four Horizon 2020 (H2020) European Union (EU)-funded projects: BOUNCE, CATCH ITN, DESIREE, and MyPal. The issues covered included patient engagement, knowledge and data-driven decision support systems, patient journey, rehabilitation, personalized diagnosis, trust, assessment of guidelines, and interoperability of information and communication technology (ICT) platforms. A series of recommendations was provided as the complex landscape of data-driven technical innovation in cancer care was portrayed.
This study aims to provide information on the current state of the art of technology and data-driven innovations for the management of cancer care through the work of four EU H2020-funded projects.
Two international workshops on ICT in the management of cancer care were held, and several topics were identified through discussion among the participants. A focus group was formulated after the second workshop, in which the status of technological and data-driven cancer management as well as the challenges, opportunities, and recommendations in this area were collected and analyzed.
Technical and data-driven innovations provide promising tools for the management of cancer care. However, several challenges must be successfully addressed, such as patient engagement, interoperability of ICT-based systems, knowledge management, and trust. This paper analyzes these challenges, which can be opportunities for further research and practical implementation and can provide practical recommendations for future work.
Technology and data-driven innovations are becoming an integral part of cancer care management. In this process, specific challenges need to be addressed, such as increasing trust and engaging the whole stakeholder ecosystem, to fully benefit from these innovations.