ABSTRACT
Dedicated brain imaging for cancer patients is seldom recommended in the absence of symptoms. There is increasing availability of non-enhanced CT (NE-CT) of the brain, mainly owing to a wider utilization of Positron Emission Tomography-CT (PET-CT) in cancer staging. Brain metastases (BM) are often hard to diagnose on NE-CT. This work aims to develop a 3D Convolutional Neural Network (3D-CNN) based on brain NE-CT to distinguish patients with and without BM. We retrospectively included NE-CT scans for 100 patients with single or multiple BM and 100 patients without brain imaging abnormalities. Patients whose largest lesion was < 5 mm were excluded. The largest tumor was manually segmented on a matched contrast-enhanced T1 weighted Magnetic Resonance Imaging (MRI), and shape radiomics were extracted to determine the size and volume of the lesion. The brain was automatically segmented, and masked images were normalized and resampled. The dataset was split into training (70%) and validation (30%) sets. Multiple versions of a 3D-CNN were developed, and the best model was selected based on accuracy (ACC) on the validation set. The median largest tumor Maximum-3D-Diameter was 2.29 cm, and its median volume was 2.81 cc. Solitary BM were found in 27% of the patients, while 49% had > 5 BMs. The best model consisted of 4 convolutional layers with 3D average pooling layers, dropout layers of 50%, and a sigmoid activation function. Mean validation ACC was 0.983 (SD: 0.020) and mean area under receiver-operating characteristic curve was 0.983 (SD: 0.023). Sensitivity was 0.983 (SD: 0.020). We developed an accurate 3D-CNN based on brain NE-CT to differentiate between patients with and without BM. The model merits further external validation.
ABSTRACT
Solitary large brain metastases (LBM) and high-grade gliomas (HGG) are sometimes hard to differentiate on MRI. The management differs significantly between these two entities, and non-invasive methods that help differentiate between them are eagerly needed to avoid potentially morbid biopsies and surgical procedures. We explore herein the performance and interpretability of an MRI-radiomics variational quantum neural network (QNN) using a quantum-annealing mutual-information (MI) feature selection approach. We retrospectively included 423 patients with HGG and LBM (> 2 cm) who had a contrast-enhanced T1-weighted (CE-T1) MRI between 2012 and 2019. After exclusion, 72 HGG and 129 LBM were kept. Tumors were manually segmented, and a 5-mm peri-tumoral ring was created. MRI images were pre-processed, and 1813 radiomic features were extracted. A set of best features based on MI was selected. MI and conditional-MI were embedded into a quadratic unconstrained binary optimization (QUBO) formulation that was mapped to an Ising-model and submitted to D'Wave's quantum annealer to solve for the best combination of 10 features. The 10 selected features were embedded into a 2-qubits QNN using PennyLane library. The model was evaluated for balanced-accuracy (bACC) and area under the receiver operating characteristic curve (ROC-AUC) on the test set. The model performance was benchmarked against two classical models: dense neural networks (DNN) and extreme gradient boosting (XGB). Shapley values were calculated to interpret sample-wise predictions on the test set. The best 10-feature combination included 6 tumor and 4 ring features. For QNN, DNN, and XGB, respectively, training ROC-AUC was 0.86, 0.95, and 0.94; test ROC-AUC was 0.76, 0.75, and 0.79; and test bACC was 0.74, 0.73, and 0.72. The two most influential features were tumor Laplacian-of-Gaussian-GLRLM-Entropy and sphericity. We developed an accurate interpretable QNN model with quantum-informed feature selection to differentiate between LBM and HGG on CE-T1 brain MRI. The model performance is comparable to state-of-the-art classical models.
Subject(s)
Brain Neoplasms , Glioma , Humans , Retrospective Studies , Area Under Curve , Brain Neoplasms/diagnostic imaging , Brain Neoplasms/pathology , Glioma/diagnostic imaging , Magnetic Resonance Imaging/methods , Neural Networks, ComputerABSTRACT
AIMS: To evaluate the effectiveness of a brief smoking cessation intervention in head and neck cancer patients (HNCP). STUDY DESIGN: A prospective randomized controlled trial that randomly assigns participants in two groups: a usual care group (UCG), and a standardized intervention group (SIG). MATERIAL AND METHODS: Patients with a confirmed diagnosis of head and neck squamous cell carcinoma (HNSCC) and who are active smokers were prospectively approached by one of 4 trained Ear-nose-throat (ENT) residents. Participants were randomized into a UCG, and a SIG consisting of a brief perioperative smoking cessation intervention based on National Institute of Health (NIH) "5A's" model along with an informative motivational document and nicotine patch therapy (NPT) offered for 8 weeks in gradually decreasing doses. OBJECTIVE: The evaluation of abstinence at 3, 6 and 12 months after enrollment. RESULTS: 56 subjects were randomized into the UCG (N = 29, 52%), and the SIG (N = 27, 48%). The overall smoking cessation rates were not statistically different between the two groups; we observed at 3 months cessation rates of 57.1% vs. 57.7% (p = 0.96); at 6 months, 42.9% vs. 24% (p = 0.148); and at 12 months, 33.3% vs. 20.8% (p = 0.318), for the UCG and the SIG respectively. CONCLUSION: This study failed to show the effectiveness of a combined brief smoking cessation approach led by and ENT resident in HNSCC patients. A multifaceted approach addressing different pharmacological treatments, factors contributing to smoking maintenance, mainly alcohol dependence and mood disturbances and dealing with relapse risks through close face-to-face or phone call follow-ups may have better outcomes and should be evaluated in upcoming trials.
Subject(s)
Head and Neck Neoplasms , Smoking Cessation , Squamous Cell Carcinoma of Head and Neck , Adult , Aged , Female , Follow-Up Studies , Humans , Male , Middle Aged , Prospective Studies , Smoking Cessation/methods , Smoking Cessation/statistics & numerical data , Time Factors , Tobacco Use Cessation Devices , Treatment OutcomeABSTRACT
Cancer of unknown primary accounts for 3-5% of all cancers for which an adequate investigation does not identify the primary tumor. The particular subset of brain metastasis in cancer of unknown primary (BMCUP) is a clinical challenge that lacks standardized diagnostic and therapeutic options. It is diagnosed predominantly in male patients in the sixth decade of age with complaints of headache, neurological dysfunction, cognitive and behavioral disturbances and seizures. The therapeutic approach to patients with BMCUP relies on local control and systemic treatment. Surgery or stereotactic radiosurgery and/or whole brain radiation therapy seems to be the cornerstone of the treatment approach to BMCUP. Systemic therapy remains essential as cancers of unknown primary are conceptually metastatic tumors. The benefits of chemotherapy were disappointing whereas those of targeted therapies and immune checkpoint inhibitors remain to be evaluated. In this Review, we address the advances in the diagnosis and treatment of BMCUP.
Subject(s)
Antineoplastic Agents/therapeutic use , Brain Neoplasms/secondary , Brain Neoplasms/therapy , Neoplasms, Unknown Primary/pathology , Radiosurgery , Biomarkers, Tumor/blood , Brain Neoplasms/pathology , Combined Modality Therapy , Humans , MaleABSTRACT
INTRODUCTION: The present study prospectively reported both physicians' and patients' assessment for toxicities, cosmetic assessment and patients' satisfaction after 3D-conformal accelerated partial breast irradiation (APBI). MATERIALS AND METHODS: From October 2007 to September 2009, 30 early breast cancer patients were enrolled in a 3D-conformal APBI Phase II trial (40 Gy/10 fractions/5 days). Treatment related toxicities and cosmetic results were assessed by both patients and physicians at each visit (at 1, 2, 6 months, and then every 6 months). Patient satisfaction was also scored. RESULTS: After a median follow-up of 27.7 months, all patients were satisfied with APBI treatment, regardless of cosmetic results or late adverse events. Good/excellent cosmetic results were noticed by 80% of patients versus 92% of cases by radiation oncologists. Breast pain was systematically underestimated by physicians (8-20% vs. 16.6-26.2%; Kappa coefficient KC=0.16-0.44). Grade 1 and 2 fibrosis and/or breast retraction occurred in 7-12% of patients and were overestimated by patients (KC=0.14-0.27). CONCLUSIONS: Present results have shown discrepancies between patient and physician assessments. In addition to the assessment of efficacy and toxicity after 3D-conformal APBI, patients' cosmetic results consideration and satisfaction should be also evaluated.
Subject(s)
Breast Neoplasms/radiotherapy , Radiotherapy, Conformal/methods , Aged , Female , Humans , Imaging, Three-Dimensional , Middle Aged , Patient Satisfaction , Radiotherapy, Conformal/adverse effectsABSTRACT
BACKGROUND: Although 3D-conformal accelerated partial breast irradiation (APBI) is widely used, several questions still remain such as what are the optimal treatment planning modalities. Indeed, some patients may have an unfavorable anatomy and/or inadequate dosimetric constraints could be fulfilled ("complex cases"). In such cases, we wondered which treatment planning modality could be applied to achieve 3D-conformal APBI (2 mini-tangents and an "en face" electron field or non-coplanar photon multiple fields; or a mixed technique combining non-coplanar photon multiple fields with an "en face" electron beam). METHODS: From October 2007 to March 2010, 55 patients with pT1N0 breast cancer were enrolled in a phase II APBI trial. Among them, 7 patients were excluded as they were considered as "complex cases". A dosimetric comparison was performed according to the 3 APBI modalities mentioned above and assessed: planning treatment volume (PTV) coverage, PTV/whole breast ratio, lung and heart distance within irradiated field and exposure of organs at risk (OAR). RESULTS: Adequate PTV coverage was obtained with the 3 different treatment planning. Regarding OAR exposure, the "mixed technique" seemed to reduce the volume of non-target breast tissue in 4 cases compared to the other techniques (in only 1 case), with the mean V50% at 44.9% (range, 13.4 - 56.9%) for the mixed modality compared to 51.1% (range, 22.4 - 63.4%) and 51.8% (range, 23.1 - 59.5%) for the reference and non-coplanar techniques, respectively. The same trend was observed for heart exposure. CONCLUSIONS: The mixed technique showed a promising trend of reducing the volume of non-target breast tissue and heart exposure doses in APBI "complex cases".
Subject(s)
Breast Neoplasms/radiotherapy , Radiotherapy Planning, Computer-Assisted/methods , Aged , Female , Humans , Middle Aged , Radiation Dosage , Radiotherapy, Adjuvant/methods , Radiotherapy, Conformal/methodsABSTRACT
BACKGROUND: Treatment of high-grade vaginal intraepithelial neoplasia (VAIN) is controversial and could include surgical excision, topical medication, brachytherapy, or other treatments. We report the results of low-dose-rate (LDR) vaginal brachytherapy for grade 3 VAIN (VAIN-3) over a 25-year period at Gustave Roussy Institute. PATIENTS AND METHODS: We retrospectively reviewed the files of all patients treated at Gustave Roussy Institute for VAIN-3 since 1985. The treatment consisted of LDR brachytherapy using a personalized vaginal mold and delivered 60 Gy to 5 mm below the vaginal mucosa. All patients had at least an annual gynecological examination, including a vaginal smear. RESULTS: Twenty-eight patients were eligible. The median follow-up was 41 months. Seven patients had a follow-up <2 years, and the median follow-up for the remaining 21 patients was 79 months. The median age at brachytherapy was 63 years (range, 38-80 years). Twenty-six patients had a history of VAIN recurring after cervical intraepithelial neoplasia and 24 had a previous hysterectomy. The median brachytherapy duration was 4.5 days. Median doses to the International Commission of Radiation Units and Measurements rectum and bladder points were 68 Gy and 45 Gy, respectively. The median prescription volume (60 Gy) was 74 cm(3). Only one "in field" recurrence occurred, corresponding to a 5- and 10-year local control rate of 93% (95% confidence interval, 70%-99%). The treatment was well tolerated, with no grade 3 or 4 late toxicity and only one grade 2 digestive toxicity. No second cancers were reported. CONCLUSION: LDR brachytherapy is an effective and safe treatment for vaginal intraepithelial neoplasia.
Subject(s)
Brachytherapy/methods , Carcinoma in Situ/radiotherapy , Uterine Cervical Dysplasia/radiotherapy , Vaginal Neoplasms/radiotherapy , Adult , Aged , Aged, 80 and over , Brachytherapy/adverse effects , Carcinoma in Situ/pathology , Carcinoma in Situ/surgery , Combined Modality Therapy , Dose-Response Relationship, Radiation , Female , Gynecological Examination , Humans , Hysterectomy , Middle Aged , Neoplasm Recurrence, Local , Retrospective Studies , Treatment Outcome , Vaginal Neoplasms/pathology , Vaginal Neoplasms/surgery , Vaginal Smears , Uterine Cervical Dysplasia/pathology , Uterine Cervical Dysplasia/surgeryABSTRACT
OBJECTIVE: To assess the tolerance of adjuvant radiotherapy in the treatment of stage I seminoma post-orchiectomy. MATERIAL AND METHODS: Between 2001 and 2006, 21 men with stage I seminoma underwent 3D conformal radiotherapy 3 to 4 weeks post-orchiectomy. The total radiation dose was 2490 cGy divided into 15 sessions. Radiation was delivered by 2 antero-posterior fields using X-ray photons of 18 MV. Two types of radiation fields were used : para-aortic and ipsilateral iliac (dog leg) or para-aortic only. The average followup was 2 years 4 months with an interval of 4 to 58 months. Tolerance of treatment was evaluated according to criteria of the RTOG. RESULTS: Median follow-up time is 30 months. Disease-free survival was 100%. The most frequently encountered acute toxicity was gastrointestinal; mainly nausea and vomiting. Tolerance to treatment was better in the group receiving para-aortic radiotherapy alone (37% of grade II gastrointestinal toxicity vs 62%) CONCLUSION: The para-aortic irradiation for stage I seminoma gave satisfactory results with a better toxicity profile than the dogleg irradiation.
Subject(s)
Seminoma/radiotherapy , Testicular Neoplasms/radiotherapy , Adult , Disease-Free Survival , Follow-Up Studies , Humans , Male , Middle Aged , Orchiectomy , Radiotherapy, Adjuvant , Seminoma/pathology , Seminoma/surgery , Testicular Neoplasms/pathology , Testicular Neoplasms/surgery , Young AdultABSTRACT
OBJECTIVE: To evaluate the response to and toxicities of chemo-radiotherapy (CT-RT) in patients with early stage Hodgkin lymphoma treated in our institution. MATERIALS AND METHODS: Retrospective study of 42 patients with early stage Hodgkin lymphoma treated between 2002 and 2007. RESULTS: The age of patients ranges from 11 to 57 with a mean of 30.7 years; the sex-ratio is 0.8 (19 males and 23 females). There are 33 cases of nodular-sclerosing Hodgkin lymphoma, 6 of mixed cellularity, one lymphocyte-rich, one interfollicular and one granulomatous. As for the stages, 31 Hodgkin lymphomas are stage IIA, 6 stage IA, 3 bulky and 2 stage IAe. The ABVD protocol was given to 38 patients, the VBVP to 3 patients and the ABV to one patient. IFRT was used with dose ranging from 19.8 to 39.6 Gy. The acute toxicity of chemotherapy was hematologic only, grade 1 anemia accounting for 11.1% and grade 2 anemia for 14.8%, grade 1 leukopenia for 51.8%, grade 2 leukopenia for 333% and grade 3 leukopenia for 14.8%. Dysphagia, radiodermitis and radiomucositis were seen after radiotherapy, accounting for 16.5%, 4.6% and 9.1% respectively. No long-term toxicity of the combined therapy was found. During the follow-up period, one relapse occurred and no death was reported. CONCLUSION: The overall survival (OS), the disease free survival (DFS) and the toxicities of the combined therapy CT-RT of the patients with early stage Hodgkin lymphoma stage IA and IIA treated in our institution were similar to those seen in the literature.
Subject(s)
Chemoradiotherapy , Hodgkin Disease/drug therapy , Hodgkin Disease/radiotherapy , Adult , Female , Hodgkin Disease/mortality , Hodgkin Disease/pathology , Humans , Male , Middle Aged , Retrospective StudiesABSTRACT
Graves' ophthalmopathy is a debilitating disease impairing the quality of life of affected individuals. The management of moderate-to-severe active Graves' ophthalmopathy is a major therapeutic challenge, and the treatment outcome is often unsatisfactory. We have carried out a retrospective study to assess the efficacy of combined orbital irradiation and systemic corticosteroids. Ten patients were included; all patients had received 20 Grays to the retrobulbar tissues in ten fractions, and oral or intravenous glucocorticoids. The main therapeutic outcome measures were the criteria of Donaldson and co-workers and a self-assessment evaluation. The quality of life outcome was also evaluated by the GO-QOL (Graves' ophthalmopathy quality of life) questionnaire. Seven patients (70%) demonstrated improvement in ocular parameters; the response was excellent in three cases, good in three cases and fair in one case. Three patients showed no response to the treatment. The self-assessment evaluation showed that 75% of patients were satisfied with the results of the treatment. Proptosis was the most responsive sign to radiation and steroids. A duration of the eye disease of more than 18 months was associated with less improvement and a higher failure of the treatment. Concerning the quality of life, the score for visual fonctionning was 882 +/- 18.2 after treatment, while the score for appearance was 63.3 +/- 23.3. In conclusion, a combination of orbital irradiation and systemic steroids is associated with 70% of favorable responses, but the quality of life is not restored in the same proportions and remains impaired after treatment.
Subject(s)
Graves Ophthalmopathy/therapy , Adult , Female , Glucocorticoids/therapeutic use , Humans , Methylprednisolone/therapeutic use , Quality of Life , Radiotherapy Dosage , Retrospective StudiesABSTRACT
BACKGROUND: The aim of this retrospective study is to evaluate the results and identify prognostic factors in early breast cancer. MATERIALS AND METHODS: One hundred breast cancers, 79 stage I and 21 stage II, had a conservative treatment between September 1993 and February 1996. Median age was 57 years; median tumor size 15 mm. Pathology was infiltrating ductal carcinoma in 88%. All patients underwent a conservative surgery followed by external radiotherapy. Twenty-eight patients received adjuvant chemotherapy and 64 patients received hormonal therapy. The median follow-up was 100 months. RESULTS: The 10 years overall survival rate was 85% and the metastasis free survival rate was 88.5%. The 10 years local control rate was 85.7%. Women less than 45 years old had a worse prognosis. CONCLUSION: These high rates of survival and local control confirm that breast conservation therapy yields favorable results, and that age is a major risk factor in women with early breast cancer.
Subject(s)
Breast Neoplasms/radiotherapy , Treatment Outcome , Adult , Age Factors , Aged , Breast Neoplasms/mortality , Female , Humans , Kaplan-Meier Estimate , Middle Aged , Neoplasm Staging , Prognosis , Retrospective StudiesABSTRACT
INTRODUCTION: The incidence of ductal carcinoma in situ (DCIS) of the breast discovered during screening mammography is rising. This finding has led to the possibility of further breast conservation. We reviewed in this article the role of radiotherapy in the context of breast conservation. MATERIAL AND METHODS: Randomized and nonrandomized trials as well as meta-analyses and textbooks dealing with radiotherapy for DCIS have been retrieved from the published literature. Databases for ongoing trials have also been checked. RESULTS: Non randomized studies showed a poor local control with surgery alone, with local recurrences varying between 20 and 40% at 10 years. The use of radiotherapy led to a significant decrease in local relapse thus giving the rationale for phase III trials evaluating the role of radiotherapy. To date there are four trials published dealing with radiotherapy for DCIS:EORTC 10853, NSABP B-17, SweDCIS and UKCCCR. All these studies showed a significant decrease in the local relapse to values around 15% at 10 years. This benefit did not however translate into any survival gain. The effect of radiotherapy was seen in all patients sub-groups. However, controversies about the necessity of irradiating all patients and about the dose of the radiation to deliver remain present. Ongoing trials trying to provide answers to these controversies are reviewed. CONCLUSIONS: Conservative surgery followed by radiotherapy to the whole breast to a dose of 50 Gy remains the standard for breast DCIS discovered with screening mammography. This treatment should be discussed with all patients until randomized data provide evidence of a low risk category that should not have adjuvant radiation. The use of a boost on the tumor bed remains to be discussed for young patients who have positive margins only until data derived from phase III trials are available.