Glioblastoma and radiotherapy: A multicenter AI study for Survival Predictions from MRI (GRASP study).

BACKGROUND: The aim was to predict survival of glioblastoma at 8 months after radiotherapy (a period allowing for completing a typical course of adjuvant temozolomide), by applying deep learning to the first brain MRI after radiotherapy completion. METHODS: Retrospective and prospective data were collected from 206 consecutive glioblastoma, isocitrate dehydrogenase -wildtype patients diagnosed between March 2014 and February 2022 across 11 UK centers. Models were trained on 158 retrospective patients from 3 centers. Holdout test sets were retrospective (n = 19; internal validation), and prospective (n = 29; external validation from 8 distinct centers). Neural network branches for T2-weighted and contrast-enhanced T1-weighted inputs were concatenated to predict survival. A nonimaging branch (demographics/MGMT/treatment data) was also combined with the imaging model. We investigated the influence of individual MR sequences; nonimaging features; and weighted dense blocks pretrained for abnormality detection. RESULTS: The imaging model outperformed the nonimaging model in all test sets (area under the receiver-operating characteristic curve, AUC P = .038) and performed similarly to a combined imaging/nonimaging model (P > .05). Imaging, nonimaging, and combined models applied to amalgamated test sets gave AUCs of 0.93, 0.79, and 0.91. Initializing the imaging model with pretrained weights from 10 000s of brain MRIs improved performance considerably (amalgamated test sets without pretraining 0.64; P = .003). CONCLUSIONS: A deep learning model using MRI images after radiotherapy reliably and accurately determined survival of glioblastoma. The model serves as a prognostic biomarker identifying patients who will not survive beyond a typical course of adjuvant temozolomide, thereby stratifying patients into those who might require early second-line or clinical trial treatment.

Changes in primary breast cancer heterogeneity may augment midtreatment MR imaging assessment of response to neoadjuvant chemotherapy.

PURPOSE: To evaluate whether changes in magnetic resonance (MR) imaging heterogeneity may aid assessment for pathologic complete response (pCR) to neoadjuvant chemotherapy (NACT) in primary breast cancer and to compare pCR with standard Response Evaluation Criteria in Solid Tumors response. MATERIALS AND METHODS: Institutional review board approval, with waiver of informed consent, was obtained for this retrospective analysis of 36 consecutive female patients, with unilateral unifocal primary breast cancer larger than 2 cm in diameter who were receiving sequential anthracycline-taxane NACT between October 2008 and October 2012. T2- and T1-weighted dynamic contrast material-enhanced MR imaging was performed before, at midtreatment (after three cycles), and after NACT. Changes in tumor entropy (irregularity) and uniformity (gray-level distribution) were determined before and after MR image filtration (for different-sized features). Entropy and uniformity for pathologic complete responders and nonresponders were compared by using the Mann-Whitney U test and receiver operating characteristic analysis. RESULTS: With NACT, there was an increase in uniformity and a decrease in entropy on T2-weighted and contrast-enhanced subtracted T1-weighted MR images for all filters (uniformity: 23.45% and 22.62%; entropy: -19.15% and -19.26%, respectively). There were eight complete pathologic responders. An area under the curve of 0.84 for T2-weighted MR imaging entropy and uniformity (P = .004 and .003) and 0.66 for size (P = .183) for pCR was found, giving a sensitivity and specificity of 87.5% and 82.1% for entropy and 87.5% and 78.6% for uniformity compared with 50% and 82.1%, respectively, for tumor size change for association with pCR. CONCLUSION: Tumors become more homogeneous with treatment. An increase in T2-weighted MR imaging uniformity and a decrease in T2-weighted MR imaging entropy following NACT may provide an earlier indication of pCR than tumor size change.

Imaging breast cancer bone metastases: current status and future directions.

The skeleton is commonly affected in the context of metastatic breast cancer and is a cause of significant morbidity in these individuals. Therapeutic options include systemic therapy, radiotherapy, and surgery given with the intent of preserving function and quality of life. As the spectrum of available therapies increases, key challenges comprise reliable diagnosis of bony metastatic disease and accurate evaluation of response that permits rapid therapeutic transition in those responding inadequately prior to development of significant skeletal morbidity. The (99m)Tc-diphosphonate bone scan remains one of the most commonly requested investigations for skeletal evaluation in patients with breast cancer. However a time lag of 3-6 months for accurate response evaluation from the start of treatment limits its utility for response evaluation in routine clinical practice or as a progression end point in the research setting. Functional imaging strategies using more tumor-specific radiopharmaceuticals show promise as an effective means of imaging response at a clinically relevant time point and are the subject of this review.

PARP inhibitors--current status and the walk towards early breast cancer.

Epithelial carcinomas in general arise as a result of the acquisition of and selection for multiple mutations in a parental somatic cell clone within the tissues of the primary organ of origin. In the last two decades genome caretakers, which function in key areas of DNA damage response, have been recognized as important tumour suppressor genes. Inactivating mutations in these genes occur both as germline and/or somatic mutations with increasing evidence of epigenetic silencing as an additional cause of loss of function. In any event, loss of function in a tumour cell pre-cursor clone leads to accelerated mutation acquisition and underpins the aetiology of the tumour. With increasing understanding of the complex network that is the DNA damage response, signaling pathways already recognized to be central to the establishment of the cancer phenotype are gaining additional roles as controllers of DNA repair. This has relevance to identification of wider populations of patients with tumours susceptible to approaches that target DNA repair deficiency. These have classically been with DNA damaging chemotherapy but the recently developed small molecule inhibitors of DNA repair enzymes such as Poly-ADP polymerases PARP-1 and PARP-2 have been shown to target tumour deficiencies in DNA repair as well sensitizing to DNA damaging therapeutics such as radiation and chemotherapy. Early phase trials with efficacy endpoints have been presented for the PARP inhibitors AG014699, olaparib, veliparib, iniparib and MK4827. The results of the first phase II trials exploring monotherapy PARP inhibitor strategies, which are based on revisiting the concept of synthetic lethality, have emerged and are reviewed herein. The clinical trials that have or are exploring combinations with DNA damaging therapy in these contexts are discussed with particular reference to breast cancer, as are biomarkers that have been proposed and are being investigated to develop optimal drug schedule and patient selection criteria for these DNA repair targeting approaches.

Long-term neurologic and peripheral vascular toxicity after chemotherapy treatment of testicular cancer.

BACKGROUND: Testicular cancer is curable in the majority of men, and persisting treatment toxicity is a concern. The authors report a cross-sectional study of the long-term effects of chemotherapy (C) on neurologic function and development of Raynaud phenomenon. METHODS: Seven hundred thirty-nine patients who were treated between 1982 and 1992 gave consent to enter the study. Patients were classified according to the receipt of C (n = 384) or no C (n = 355). Patients completed a general health questionnaire and a quality-of-life form (the European Organization for Research and Treatment of Cancer Quality-of-Life C30 questionnaire with testicular module). Symptom scores of 3 or 4 were considered clinically significant. Patients were assessed in the clinic, and clinical history was used to diagnose Raynaud phenomenon (RP) and tinnitus. Examinations included peripheral nerve function testing for light touch and vibration sense. Five hundred seventy-seven patients underwent audiometry. RESULTS: On physician assessment, peripheral neuropathy and RP were more common after C (21.7% vs 9.1% [P<.001] and 20.3% vs 1.7% [P<.001], respectively). Similar results were obtained for symptom scores (12.5% vs 5.5% [P = .002] and 9.7% vs 3.7% [P<.001], respectively). On multivariate analysis, for peripheral neuropathy, the significant predictors were cisplatin dose, carboplatin dose, and age. For RP, the significant predictor was bleomycin. Significant differences in hearing thresholds were noted at 8000 hertz only and, on multivariate analysis, were related to age, cisplatin dose, and vincristine dose. Auditory symptom scores did not differ between groups. CONCLUSIONS: With long-term follow-up, peripheral neuropathy and RP remained detectable in approximately 20% of patients and caused significant symptoms in 10% of patients. Detectable effects on high frequency remained but caused little symptomatic problem. These effects persisted and were related to the cumulative chemotherapy dose.