Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to aid in rapid evaluation of CT scans ...for differentiation of COVID-19 findings from other clinical entities. Here we show that a series of deep learning algorithms, trained in a diverse multinational cohort of 1280 patients to localize parietal pleura/lung parenchyma followed by classification of COVID-19 pneumonia, can achieve up to 90.8% accuracy, with 84% sensitivity and 93% specificity, as evaluated in an independent test set (not included in training and validation) of 1337 patients. Normal controls included chest CTs from oncology, emergency, and pneumonia-related indications. The false positive rate in 140 patients with laboratory confirmed other (non COVID-19) pneumonias was 10%. AI-based algorithms can readily identify CT scans with COVID-19 associated pneumonia, as well as distinguish non-COVID related pneumonias with high specificity in diverse patient populations.
Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, application of these models in clinically realistic environments can result in poor ...generalization and decreased accuracy, mainly due to the domain shift across different hospitals, scanner vendors, imaging protocols, and patient populations etc. Common transfer learning and domain adaptation techniques are proposed to address this bottleneck. However, these solutions require data (and annotations) from the target domain to retrain the model, and is therefore restrictive in practice for widespread model deployment. Ideally, we wish to have a trained (locked) model that can work uniformly well across unseen domains without further training. In this paper, we propose a deep stacked transformation approach for domain generalization. Specifically, a series of {n} stacked transformations are applied to each image during network training. The underlying assumption is that the "expected" domain shift for a specific medical imaging modality could be simulated by applying extensive data augmentation on a single source domain, and consequently, a deep model trained on the augmented "big" data (BigAug) could generalize well on unseen domains. We exploit four surprisingly effective, but previously understudied, image-based characteristics for data augmentation to overcome the domain generalization problem. We train and evaluate the BigAug model (with {n}={9} transformations) on three different 3D segmentation tasks (prostate gland, left atrial, left ventricle) covering two medical imaging modalities (MRI and ultrasound) involving eight publicly available challenge datasets. The results show that when training on relatively small dataset (n = 10~32 volumes, depending on the size of the available datasets) from a single source domain: (i) BigAug models degrade an average of 11%(Dice score change) from source to unseen domain, substantially better than conventional augmentation (degrading 39%) and CycleGAN-based domain adaptation method (degrading 25%), (ii) BigAug is better than "shallower" stacked transforms (i.e. those with fewer transforms) on unseen domains and demonstrates modest improvement to conventional augmentation on the source domain, (iii) after training with BigAug on one source domain, performance on an unseen domain is similar to training a model from scratch on that domain when using the same number of training samples. When training on large datasets (n = 465 volumes) with BigAug, (iv) application to unseen domains reaches the performance of state-of-the-art fully supervised models that are trained and tested on their source domains. These findings establish a strong benchmark for the study of domain generalization in medical imaging, and can be generalized to the design of highly robust deep segmentation models for clinical deployment.
In this study involving 2103 men with elevated PSA levels, the use of both MRI-targeted and 12-core systematic biopsies was more effective at detecting clinically significant prostate cancers than ...either biopsy method alone.
PSMA PET and Radionuclide Therapy in Prostate Cancer Bouchelouche, Kirsten, MD, DMSc; Turkbey, Baris, MD, FSAR; Choyke, Peter L., MD FACR
Seminars in nuclear medicine,
11/2016, Letnik:
46, Številka:
6
Journal Article
Recenzirano
Odprti dostop
Prostate cancer (PCa) is the most common malignancy in men and a major cause of cancer death. Accurate imaging plays an important role in diagnosis, staging, restaging, detection of biochemical ...recurrence, and for therapy of patients with PCa. Because no effective treatment is available for advanced PCa, there is an urgent need to develop new and more effective therapeutic strategies. To optimize treatment outcome, especially in high-risk patients with PCa, therapy for PCa is moving rapidly toward personalization. Medical imaging, including positron emission tomography (PET)/computed tomography (CT), plays an important role in personalized medicine in oncology. In the recent years, much focus has been on prostate-specific membrane antigen (PSMA) as a promising target for imaging and therapy with radionuclides, as it is upregulated in most PCa. In the prostate, one potential role for PSMA PET imaging is to help guide focal therapy. Several studies have shown great potential of PSMA PET/CT for initial staging, lymph node staging, and detection of recurrence of PCa, even at very low prostate-specific antigen values after primary therapy. Furthermore, studies have shown that PSMA PET/CT has a higher detection rate than choline PET/CT. Radiolabeled PSMA ligands for therapy show promise in several studies with metastatic PCa and is an area of active investigation. The “image and treat” strategy, with radiolabeled PSMA ligands, has the potential to improve the treatment outcome of patients with PCa and is paving the way for precision medicine in PCa. The aim of this review is to give an overview of recent advancement in PSMA PET and radionuclide therapy for PCa.
High-quality evidence shows that MRI in biopsy-naive men can reduce the number of men who need prostate biopsy and can reduce the number of diagnoses of clinically insignificant cancers that are ...unlikely to cause harm. In men with prior negative biopsy results who remain under persistent suspicion, MRI improves the detection and localization of life-threatening prostate cancer with greater clinical utility than the current standard of care, systematic transrectal US-guided biopsy. Systematic analyses show that MRI-directed biopsy increases the effectiveness of the prostate cancer diagnosis pathway. The incorporation of MRI-directed pathways into clinical care guidelines in prostate cancer detection has begun. The widespread adoption of the Prostate Imaging Reporting and Data System (PI-RADS) for multiparametric MRI data acquisition, interpretation, and reporting has promoted these changes in practice. The PI-RADS MRI-directed biopsy pathway enables the delivery of key diagnostic benefits to men suspected of having cancer based on clinical suspicion. Herein, the PI-RADS Steering Committee discusses how the MRI pathway should be incorporated into routine clinical practice and the challenges in delivering the positive health impacts needed by men suspected of having clinically significant prostate cancer.
The purpose of this article is to highlight the potential challenges associated with the Prostate Imaging Reporting and Data System, version 2 (PI-RADS v2), and to offer, when possible, suggestions ...and ideas for improvement.
PI-RADS v2 offers clear improvements to its earlier version and will greatly benefit the prostate MRI community. Nonetheless, caution remains on the basis of early user experience, and potential ambiguities and gaps of PI-RADS v2 are noted. Continued data-driven clarification and refinement of the guidelines will be invaluable for PI-RADS v2 to achieve its goal of improving patient care.
Imaging techniques are used to identify local recurrence of prostate cancer (PCa) for salvage therapy and to exclude metastases that should be addressed with systemic therapy. For magnetic resonance ...imaging (MRI), a reduction in the variability of acquisition, interpretation, and reporting is required to detect local PCa recurrence in men with biochemical relapse after local treatment with curative intent.
To propose a standardised method for image acquisition and assessment of PCa local recurrence using MRI after radiation therapy (RP) and radical prostatectomy (RT).
Prostate Imaging for Recurrence Reporting (PI-RR) was formulated using the existing literature. An international panel of experts conducted a nonsystematic review of the literature. The PI-RR system was created via consensus through a combination of face-to-face and online discussions.
Similar to with PI-RADS, based on the best available evidence and expert opinion, the minimum acceptable MRI parameters for detection of recurrence after radiation therapy and radical prostatectomy are set. Also, a simplified and standardised terminology and content of the reports that use five assessment categories to summarise the suspicion of local recurrence (PI-RR) are designed. PI-RR scores of 1 and 2 are assigned to lesions with a very low and low likelihood of recurrence, respectively. PI-RR 3 is assigned if the presence of recurrence is uncertain. PI-RR 4 and 5 are assigned for a high and very high likelihood of recurrence, respectively. PI-RR is intended to be used in routine clinical practice and to facilitate data collection and outcome monitoring for research.
This paper provides a structured reporting system (PI-RR) for MRI evaluation of local recurrence of PCa after RT and RP.
A new method called PI-RR was developed to promote standardisation and reduce variations in the acquisition, interpretation, and reporting of magnetic resonance imaging for evaluating local recurrence of prostate cancer and guiding therapy.
Prostate Imaging for Recurrence Reporting (PI-RR) is a 5-point assessment scale for magnetic resonance imaging evaluation of recurrence. PI-RR is designed to assess the likelihood of local relapse after radiation therapy and radical prostatectomy and to guide treatment.
Purpose To characterize clinically important prostate cancers missed at multiparametric (MP) magnetic resonance (MR) imaging. Materials and Methods The local institutional review board approved this ...HIPAA-compliant retrospective single-center study, which included 100 consecutive patients who had undergone MP MR imaging and subsequent radical prostatectomy. A genitourinary pathologist blinded to MP MR findings outlined prostate cancers on whole-mount pathology slices. Two readers correlated mapped lesions with reports of prospectively read MP MR images. Readers were blinded to histopathology results during prospective reading. At histopathologic examination, 80 clinically unimportant lesions (<5 mm; Gleason score, 3+3) were excluded. The same two readers, who were not blinded to histopathologic findings, retrospectively reviewed cancers missed at MP MR imaging and assigned a Prostate Imaging Reporting and Data System (PI-RADS) version 2 score to better understand false-negative lesion characteristics. Descriptive statistics were used to define patient characteristics, including age, prostate-specific antigen (PSA) level, PSA density, race, digital rectal examination results, and biopsy results before MR imaging. Student t test was used to determine any demographic differences between patients with false-negative MP MR imaging findings and those with correct prospective identification of all lesions. Results Of the 162 lesions, 136 (84%) were correctly identified with MP MR imaging. Size of eight lesions was underestimated. Among the 26 (16%) lesions missed at MP MR imaging, Gleason score was 3+4 in 17 (65%), 4+3 in one (4%), 4+4 in seven (27%), and 4+5 in one (4%). Retrospective PI-RADS version 2 scores were assigned (PI-RADS 1, n = 8; PI-RADS 2, n = 7; PI-RADS 3, n = 6; and PI-RADS 4, n = 5). On a per-patient basis, MP MR imaging depicted clinically important prostate cancer in 99 of 100 patients. At least one clinically important tumor was missed in 26 (26%) patients, and lesion size was underestimated in eight (8%). Conclusion Clinically important lesions can be missed or their size can be underestimated at MP MR imaging. Of missed lesions, 58% were not seen or were characterized as benign findings at second-look analysis. Recognition of the limitations of MP MR imaging is important, and new approaches to reduce this false-negative rate are needed.
RSNA, 2017 Online supplemental material is available for this article.