Building a high-resolution T2-weighted MR-based probabilistic model of tumor occurrence in the prostate.

PURPOSE: We present a method for generating a T2 MR-based probabilistic model of tumor occurrence in the prostate to guide the selection of anatomical sites for targeted biopsies and serve as a diagnostic tool to aid radiological evaluation of prostate cancer. MATERIALS AND METHODS: In our study, the prostate and any radiological findings within were segmented retrospectively on 3D T2-weighted MR images of 266 subjects who underwent radical prostatectomy. Subsequent histopathological analysis determined both the ground truth and the Gleason grade of the tumors. A randomly chosen subset of 19 subjects was used to generate a multi-subject-derived prostate template. Subsequently, a cascading registration algorithm involving both affine and non-rigid B-spline transforms was used to register the prostate of every subject to the template. Corresponding transformation of radiological findings yielded a population-based probabilistic model of tumor occurrence. The quality of our probabilistic model building approach was statistically evaluated by measuring the proportion of correct placements of tumors in the prostate template, i.e., the number of tumors that maintained their anatomical location within the prostate after their transformation into the prostate template space. RESULTS: Probabilistic model built with tumors deemed clinically significant demonstrated a heterogeneous distribution of tumors, with higher likelihood of tumor occurrence at the mid-gland anterior transition zone and the base-to-mid-gland posterior peripheral zones. Of 250 MR lesions analyzed, 248 maintained their original anatomical location with respect to the prostate zones after transformation to the prostate. CONCLUSION: We present a robust method for generating a probabilistic model of tumor occurrence in the prostate that could aid clinical decision making, such as selection of anatomical sites for MR-guided prostate biopsies.

Quantitative bone scan lesion area as an early surrogate outcome measure indicative of overall survival in metastatic prostate cancer.

A clinical validation of the bone scan lesion area (BSLA) as a quantitative imaging biomarker was performed in metastatic castration-resistant prostate cancer (mCRPC). BSLA was computed from whole-body bone scintigraphy at baseline and week 12 posttreatment in a cohort of 198 mCRPC subjects (127 treated and 71 placebo) from a clinical trial involving a different drug from the initial biomarker development. BSLA computation involved automated image normalization, lesion segmentation, and summation of the total area of segmented lesions on bone scan AP and PA views as a measure of tumor burden. As a predictive biomarker, treated subjects with baseline BSLA [Formula: see text] had longer survival than those with higher BSLA ([Formula: see text] and [Formula: see text]). As a surrogate outcome biomarker, subjects were categorized as progressive disease (PD) if the BSLA increased by a prespecified 30% or more from baseline to week 12 and non-PD otherwise. Overall survival rates between PD and non-PD groups were statistically different ([Formula: see text] and [Formula: see text]). Subjects without PD at week 12 had longer survival than subjects with PD: median 398 days versus 280 days. BSLA has now been demonstrated to be an early surrogate outcome for overall survival in different prostate cancer drug treatments.

Bone tumor segmentation on bone scans using context information and random forests.

Bone tumor segmentation on bone scans has recently been adopted as a basis for objective tumor assessment in several phase II and III clinical drug trials. Interpretation can be difficult due to the highly sensitive but non-specific nature of bone tumor appearance on bone scans. In this paper we present a machine learning approach to segmenting tumors on bone scans, using intensity and context features aimed at addressing areas prone to false positives. We computed the context features using landmark points, identified by a modified active shape model. We trained a random forest classifier on 100 and evaluated on 73 prostate cancer subjects from a multi-center clinical trial. A reference segmentation was provided by a board certified radiologist. We evaluated our learning based method using the Jaccard index and compared against the state of the art, rule based method. Results showed an improvement from 0.50 +/- 0.31 to 0.57 +/- 0.27. We found that the context features played a significant role in the random forest classifier, helping to correctly classify regions prone to false positives.

Computer-aided quantitative bone scan assessment of prostate cancer treatment response.

OBJECTIVE: The development and evaluation of a computer-aided bone scan analysis technique to quantify changes in tumor burden and assess treatment effects in prostate cancer clinical trials. METHODS: We have developed and report on a commercial fully automated computer-aided detection (CAD) system. Using this system, scan images were intensity normalized, and then lesions were identified and segmented by anatomic region-specific intensity thresholding. Detected lesions were compared against expert markings to assess the accuracy of the CAD system. The metrics Bone Scan Lesion Area, Bone Scan Lesion Intensity, and Bone Scan Lesion Count were calculated from identified lesions, and their utility in assessing treatment effects was evaluated by analyzing before and after scans from metastatic castration-resistant prostate cancer patients: 10 treated and 10 untreated. In this study, patients were treated with cabozantinib, a MET/vascular endothelial growth factor inhibitor resulting in high rates of resolution of bone scan abnormalities. RESULTS: Our automated CAD system identified bone lesion pixels with 94% sensitivity, 89% specificity, and 89% accuracy. Significant differences in changes from baseline were found between treated and untreated groups in all assessed measurements derived by our system. The most significant measure, Bone Scan Lesion Area, showed a median (interquartile range) change from baseline at week 6 of 7.13% (27.61) in the untreated group compared with -73.76% (45.38) in the cabozantinib-treated group (P=0.0003). CONCLUSION: Our system accurately and objectively identified and quantified metastases in bone scans, allowing for interpatient and intrapatient comparison. It demonstrates potential as an objective measurement of treatment effects, laying the foundation for validation against other clinically relevant outcome measures.

An automatic computer-aided detection system for meniscal tears on magnetic resonance images.

Knee-related injuries including meniscal tears are common in both young athletes and the aging population, and require accurate diagnosis and surgical intervention when appropriate. With proper techniques and radiologists' experienced skills, confidence in detection of meniscal tears can be quite high. This paper develops a novel computer-aided detection (CAD) diagnostic system for automatic detection of meniscal tears in the knee. Evaluation of this CAD system using an archived database of images from 40 individuals with suspected knee injuries indicates that the sensitivity and specificity of the proposed CAD system are 83.87% and 75.19%, respectively, compared to the mean sensitivity and specificity of 77.41% and 81.39%, respectively, obtained by experienced radiologists in routine diagnosis without using the CAD. The experimental results suggest that the developed CAD system has great potential and promise in automatic detection of both simple and complex meniscal tears of the knee.