End-to-end prostate cancer detection in bpMRI via 3D CNNs: Effects of attention mechanisms, clinical priori and decoupled false positive reduction

Saha, Anindo; Hosseinzadeh, Matin; Huisman, Henkjan

doi:10.1016/j.media.2021.102155

Cited by 106 publications

(113 citation statements)

References 43 publications

Supporting

Mentioning

102

Contrasting

Unclassified

Order By: Relevance

“…A candidate lesion was considered a true positive if the DICE similarity coefficient with the ground truth (calculated in 3D between the whole extracted candidate lesion volume and the tumor ground truth volume) was at least 0.1. This threshold was set in line with well-established previously published studies of the same nature considering other cancer diseases [ 10 , 28 ] as it addresses the clinical need for object-level localization, while also taking into account the non-overlapping nature of objects in 3D.…”

Section: Methodsmentioning

confidence: 99%

Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography

Alves¹,

Schuurmans²,

Litjens

et al. 2022

Cancers

Self Cite

View full text Add to dashboard Cite

Early detection improves prognosis in pancreatic ductal adenocarcinoma (PDAC), but is challenging as lesions are often small and poorly defined on contrast-enhanced computed tomography scans (CE-CT). Deep learning can facilitate PDAC diagnosis; however, current models still fail to identify small (<2 cm) lesions. In this study, state-of-the-art deep learning models were used to develop an automatic framework for PDAC detection, focusing on small lesions. Additionally, the impact of integrating the surrounding anatomy was investigated. CE-CT scans from a cohort of 119 pathology-proven PDAC patients and a cohort of 123 patients without PDAC were used to train a nnUnet for automatic lesion detection and segmentation (nnUnet_T). Two additional nnUnets were trained to investigate the impact of anatomy integration: (1) segmenting the pancreas and tumor (nnUnet_TP), and (2) segmenting the pancreas, tumor, and multiple surrounding anatomical structures (nnUnet_MS). An external, publicly available test set was used to compare the performance of the three networks. The nnUnet_MS achieved the best performance, with an area under the receiver operating characteristic curve of 0.91 for the whole test set and 0.88 for tumors <2 cm, showing that state-of-the-art deep learning can detect small PDAC and benefits from anatomy information.

show abstract

Section: Methodsmentioning

confidence: 99%

Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography

Alves¹,

Schuurmans²,

Litjens

et al. 2022

Cancers

Self Cite

View full text Add to dashboard Cite

show abstract

“…Materials We used 200 prostate bpMRI (T2W, high b-value DWI, ADC) exams from the publiclyavailable ProstateX dataset [18], paired with voxel-level delineations of WG, TZ, PZ and csPCa [19]. All images were resampled to 0.5 × 0.5 × 3.0 mm 3 resolution, center-cropped to 160 × 160 × 20 voxels and intensity-normalized (T2W, DWI: z-score; ADC: linear) [20], prior to usage.…”

Section: Experiments and Analysismentioning

confidence: 99%

Anatomical and Diagnostic Bayesian Segmentation in Prostate MRI $-$Should Different Clinical Objectives Mandate Different Loss Functions?

Saha¹,

S.²,

Linmans³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We hypothesize that probabilistic voxel-level classification of anatomy and malignancy in prostate MRI, although typically posed as near-identical segmentation tasks via U-Nets, require different loss functions for optimal performance due to inherent differences in their clinical objectives. We investigate distribution, region and boundary-based loss functions for both tasks across 200 patient exams from the publicly-available ProstateX dataset. For evaluation, we conduct a thorough comparative analysis of model predictions and calibration, measured with respect to multi-class volume segmentation of the prostate anatomy (whole-gland, transitional zone, peripheral zone), as well as, patient-level diagnosis and lesion-level detection of clinically significant prostate cancer. Notably, we find that distribution-based loss functions (in particular, focal loss) are well-suited for diagnostic or panoptic segmentation tasks such as lesion detection, primarily due to their implicit property of inducing better calibration. Meanwhile, (with the exception of focal loss) both distribution and region/boundary-based loss functions perform equally well for anatomical or semantic segmentation tasks, such as quantification of organ shape, size and boundaries.

show abstract

“…This histologic level of performance matched the performance of general radiologists who participated in the readings of the prospective MRI-First study [10] but is below the performance of the study's expert readers (91% sensitivity at a false-positive detection rate of 23%), and of the readers of the 4M study [11]. At this operating point, there was a moderate agreement between their DL-CAD with expert radiologists (kappa = 0.53) and histopathology readings (kappa = 0.50) [8]. Here we should note that when radiologists and CAD agree on the likely presence of suspicious lesions, the positive predictive value for GG ≥ 2 cancers increases without affecting the negative predictive value [12].…”

mentioning

confidence: 90%

“…With these general considerations in mind, Hosseinzadeh et al reported on the performance of their deep-learning (DL) CAD model for the automated detection and classification of lesions that are likely to harbour csPCa lesions [8,9]. Their multistage architecture reduced the false-positive detection rates while maintaining high sensitivity for the presence of high-suspicion lesions using bi-parametric MRI.…”

mentioning

confidence: 99%

“…Furthermore, radiologists' determinations on the likely nature of the CAD detected lesions as used in the current study are not accurate because of the dependence of predictive value for csPCa on the PI-RADS category. Despite this, a radiologist's determined false-detection rate per case metric can still be useful because fewer suspicious lesions can help lower biopsy core numbers and over-diagnosis rates [8,9].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Assessing the clinical performance of artificial intelligence software for prostate cancer detection on MRI

et al. 2022

View full text Add to dashboard Cite

End-to-end prostate cancer detection in bpMRI via 3D CNNs: Effects of attention mechanisms, clinical priori and decoupled false positive reduction

Cited by 106 publications

References 43 publications

Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography

Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography

Anatomical and Diagnostic Bayesian Segmentation in Prostate MRI $-$Should Different Clinical Objectives Mandate Different Loss Functions?

Assessing the clinical performance of artificial intelligence software for prostate cancer detection on MRI

Contact Info

Product

Resources

About